Abstract
A comprehensive fault diagnosis method of rolling bearing about noise interference, fault feature extraction, and identification was proposed. Based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), detrended fluctuation analysis (DFA), and improved wavelet thresholding, a denoising method of CEEMDAN-DFA-improved wavelet threshold function was presented to reduce the distortion of the noised signal. Based on quantum-behaved particle swarm optimization (QPSO), multiscale permutation entropy (MPE), and support vector machine (SVM), the QPSO-MPE-SVM method was presented to construct the fault-features sets and realize fault identification. Simulation and experimental platform verification showed that the proposed comprehensive diagnosis method not only can better remove the noise interference and maintain the original characteristics of the signal by CEEMDAN-DFA-improved wavelet threshold function, but also overcome overlapping MPE values by the QPSO-optimizing MPE parameters to separate the features of different fault types. The experimental results showed that the fault identification accuracy of the fault diagnosis can reach 95%, which is a great improvement compared with the existing methods.
Highlights
Rolling bearings are the most important parts of rotating machinery and are widely used in modern mechanized equipment [1,2]
This paper proposed a comprehensive rolling bearing fault feature extraction and identification method based on the combination of quantum-behaved particle swarm optimization (QPSO)-multiscale permutation entropy (MPE)-support vector machine (SVM)
This paper proposed a CEEMDAN-detrended fluctuation analysis (DFA)-improved wavelet threshold denoising method and QPSO-MPE-SVM fault feature extraction and identification method, the purpose being to realize the fault diagnosis of the rolling-bearing vibration signal
Summary
Rolling bearings are the most important parts of rotating machinery and are widely used in modern mechanized equipment [1,2]. In order to improve identification accuracy of rolling bearings with nonlinear and nonstationary vibration signals, Chen et al [17] proposed a novel fault diagnosis method based on wavelet thresholding denoising and CMEEMDAN with adaptive noise. The method uses the CEEMDAN algorithm to decompose the vibration signal, performs detrended fluctuation analysis (DFA) on the obtained eigenmode function (IMF), calculates the scalar function value of each IMF component, selects the noise-dominated. This paper proposed a comprehensive rolling bearing fault feature extraction and identification method based on the combination of QPSO-MPE-SVM. The method uses the CEEMDAN algorithm to decompose the vibration signal, performs DFA on the obtained IMF, calculates the scalar function value of each IMF component, selects the noise-dominated IMF component, and applies an improved wavelet threshold function to denoise it.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
